When orthodontists trace cephalometric radiographs, they follow a structured workflow: identify the soft tissue profile, partition the skull into anatomical regions, trace contours, and locate landmarks using geometric definitions—yet no automated system replicates this reasoning. We present a five phase anatomy-guided initialization pipeline that translates this clinical workflow into computational operations, producing confidence-weighted spatial attention priors for a downstream HRNet-W32 detector. On 1,502 radiographs from three sources spanning 7+ imaging devices, the system achieves 1.04mm mean radial error on 25 landmarks—surpassing prior state-of-the-art (1.23mm on 19 landmarks) by 15.4%, with twelve landmarks below 1 mm. A three-way controlled ablation reveals two striking findings. First, removing anatomical priors does not merely slow convergence—it destroys generalization: both models converge to ∼1.03mm on validation, but diverge to 1.94 vs. 1.04mm on the test set. Second, replacing anatomical priors with random-position Gaussians produces even worse generalization (2.24 mm), confirming that the improvement derives from anatomically correct positioning, not additional input channels. Clinical domain knowledge encoded as spatial priors provides an inductive bias that architecture and data augmentation alone do not provide.
Mohapatra et al. (Mon,) studied this question.